feat(attachment, llm): support binary attachments#423
Merged
Conversation
The toolkit now supports binary attachments, such as images and PDFs, allowing users to provide non-textual context to LLMs. This is achieved by detecting file types via magic bytes using the `infer` crate and imposing a 10 MiB safety limit on binary data. Provider implementations have been updated to handle these attachments natively. For example, Anthropic uses document blocks, Google uses inline data, and OpenAI uses image/file content items. Text-based attachments continue to be serialized as XML for providers that do not support native document structures. Internal changes include refactoring `Thread` decomposition to pass raw `Attachment` objects to providers, and updating the `Handler` trait to support upfront validation of local files. Signed-off-by: Jean Mertz <git@jeanmertz.com>
Signed-off-by: Jean Mertz <git@jeanmertz.com>
Signed-off-by: Jean Mertz <git@jeanmertz.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
JP now supports binary attachments, such as images and PDFs, allowing users to provide non-textual context to LLMs. This is achieved by detecting file types via magic bytes using the
infercrate and imposing a 10 MiB safety limit on binary data.Provider implementations have been updated to handle these attachments natively. For example, Anthropic uses document blocks, Google uses inline data, and OpenAI uses image/file content items. Text-based attachments continue to be serialized as XML for providers that do not support native document structures.
Internal changes include refactoring
Threaddecomposition to pass rawAttachmentobjects to providers, and updating theHandlertrait to support upfront validation of local files.